INDEX

Explanations

proposals

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

ows

-0.27

çķĮ

-0.27

 bound

-0.26

icks

-0.26

æĢĢæĬ±

-0.26

 soap

-0.26

çļĦè§Ĵèī²

-0.26

bags

-0.25

ijo

-0.25

çį¾

-0.25

POSITIVE LOGITS

oppable

0.27

íĨµ

0.26

URRE

0.25

oblin

0.25

urre

0.25

åĬ

0.25

uity

0.24

åĲı

0.24

 Sung

0.24

&_

0.23

Activations Density 0.007%

proposals

No Comments

No Known Activations