INDEX

Explanations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è§Ĵåº¦æĿ¥çľĭ

-0.27

åĪĨåŃĲ

-0.27

--,

-0.26

çļĦåĨ³å¿ĥ

-0.25

è®©ä»ĸä»¬

-0.25

 institute

-0.25

æĶ¾æīĭ

-0.24

_TESTS

-0.24

XS

-0.24

oreal

-0.23

POSITIVE LOGITS

ongs

0.29

ells

0.27

 toler

0.27

was

0.27

ktop

0.27

alink

0.25

tol

0.25

 Ø§ÙĦÙħÙĪØ§

0.24

ç¾½

0.24

 powerful

0.24

Activations Density 0.004%

Subscribe

No Comments

No Known Activations