INDEX

Explanations

reflex

np_max-act · gemini-2.0-flash

occurrences of the term “reflex” and its morphological variants across medical and technical contexts.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uzu

-0.26

ç¨ł

-0.26

Brain

-0.25

å½¢æĢģ

-0.25

rij

-0.25

icism

-0.24

tsy

-0.24

room

-0.24

Ð±Ñĥ

-0.23

Ð·Ð¾Ð»

-0.23

POSITIVE LOGITS

ynes

0.29

(flag

0.26

mith

0.25

çľŁè¯ļ

0.25

 flag

0.25

inally

0.24

èĮħ

0.24

rams

0.24

 Contemporary

0.24

alar

0.24

Activations Density 43.554%

reflex

occurrences of the term “reflex” and its morphological variants across medical and technical contexts.

No Comments

No Known Activations