INDEX

Explanations

Non-english/technical text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 themselves

-0.38

inke

-0.28

aldi

-0.28

keit

-0.27

 ÑģÐ°Ð¼Ð¸

-0.27

sav

-0.27

 alike

-0.27

 chunks

-0.26

å®¢å®¶

-0.26

chunks

-0.26

POSITIVE LOGITS

æĺ¯ä¸ª

0.30

ares

0.29

å°½

0.28

mits

0.27

alue

0.27

çķĻ

0.26

 Barg

0.26

çĻ¾

0.26

 history

0.26

LEG

0.26

Activations Density 0.001%

Non-english/technical text

No Comments

No Known Activations