INDEX

Explanations

Pronouns

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

ARA

-0.27

aring

-0.26

çħ

-0.26

Ĥ¤

-0.26

áº¥m

-0.25

arem

-0.25

éķ¿éĢĶ

-0.25

å¯®

-0.24

ingo

-0.24

appa

-0.24

POSITIVE LOGITS

.asList

0.26

uell

0.25

 popul

0.25

 aided

0.25

èī¯æĢ§

0.25

uum

0.24

uden

0.24

æĪĳåĸľæ¬¢

0.24

lest

0.24

/actions

0.24

Activations Density 0.001%

Pronouns

No Comments

No Known Activations