INDEX

Explanations

medical research

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

-0.29

PK

-0.28

æ²¿çĿĢ

-0.27

 frames

-0.27

èĤ¯å®ļ

-0.26

 frame

-0.26

iture

-0.25

æ²¿

-0.25

 Convers

-0.25

èĩ´çĻĮ

-0.25

POSITIVE LOGITS

uids

0.32

agus

0.29

èĬ

0.29

eut

0.28

jom

0.27

ÑģÐ¾Ñģ

0.27

èĢģäººå®¶

0.26

 HOLD

0.26

é³Į

0.26

ernes

0.25

Activations Density 0.007%

medical research

No Comments

No Known Activations