INDEX

Explanations

biology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åľĴ

-0.31

åĽŃ

-0.29

çıŃ

-0.26

?action

-0.26

pap

-0.26

 scen

-0.26

 scalp

-0.25

usted

-0.25

 coherent

-0.25

èº«ç©¿

-0.25

POSITIVE LOGITS

salt

0.34

hom

0.31

Sal

0.30

é²«

0.28

 deposited

0.28

sal

0.28

enti

0.28

 salt

0.28

 Salt

0.27

Salt

0.26

Activations Density 0.012%

biology

No Comments

No Known Activations