INDEX

Explanations

Code with "8"

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

uko

-0.27

ihil

-0.27

DidEnter

-0.26

private

-0.25

ibil

-0.25

iap

-0.24

thumb

-0.24

 Alle

-0.24

 Herr

-0.24

 private

-0.23

POSITIVE LOGITS

åģı

0.26

å¡«è¡¥

0.26

ricks

0.26

çļĦåģļæ³ķ

0.25

çªĿ

0.25

/email

0.24

ç±į

0.24

aroo

0.24

-det

0.24

tingham

0.23

Activations Density 0.001%

Code with "8"

No Comments

No Known Activations