INDEX

Explanations

and

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 brethren

-0.28

å°ıæĹ¶åĢĻ

-0.27

 attacked

-0.25

Requested

-0.25

leanup

-0.25

remen

-0.24

çĶļèĩ³

-0.24

éĺŁåıĭ

-0.24

_FORWARD

-0.24

æıĲè´¨

-0.24

POSITIVE LOGITS

 role

0.29

 Sell

0.28

 natural

0.27

ercul

0.27

 roles

0.27

 layered

0.26

 neural

0.26

à¹Ħà¸£

0.26

 modes

0.25

role

0.25

Activations Density 0.003%

and

No Comments

No Known Activations