INDEX

Explanations

common words and phrases

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

 primarily

-0.28

rite

-0.28

åıĹæ¬¢è¿İ

-0.26

_NC

-0.25

 Finds

-0.24

è§ĨåĬĽ

-0.24

erglass

-0.24

ysical

-0.23

xit

-0.23

adius

-0.23

POSITIVE LOGITS

asts

0.26

ç¯¦

0.26

votes

0.25

sod

0.25

-song

0.25

æ¨±

0.25

ibr

0.25

 therap

0.24

 bevor

0.24

ä¹ĭéĻħ

0.24

Activations Density 0.004%

common words and phrases

No Comments

No Known Activations