INDEX

Explanations

bugs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 hands

-0.28

([&

-0.25

è¾Ľ

-0.25

åħĪå¤©

-0.24

 Minh

-0.24

insic

-0.24

ORA

-0.24

prise

-0.24

æ¸Ĭ

-0.24

 statement

-0.23

POSITIVE LOGITS

aign

0.30

ÐºÐ¾Ñģ

0.28

POSITE

0.28

 Vict

0.27

æ²ı

0.27

_FOUND

0.26

 Challenger

0.26

iens

0.25

acb

0.25

ired

0.25

Activations Density 0.015%

bugs

No Comments

No Known Activations