INDEX

Explanations

factor

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

æĬĬä»ĸ

-0.28

ãĥŃãĥ³

-0.27

indr

-0.27

åħļåĴĮ

-0.26

LI

-0.26

 organisers

-0.26

lix

-0.26

 households

-0.26

 lint

-0.25

 repost

-0.25

POSITIVE LOGITS

endez

0.28

irtual

0.28

à¸±à¸ĩ

0.27

åĲĮæĥħ

0.27

arrival

0.26

oplevel

0.26

orch

0.26

entication

0.25

 arrival

0.25

ullet

0.25

Activations Density 0.085%

factor

No Comments

No Known Activations