INDEX

Explanations

computer authentication/security

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ìļķ

-0.29

å§Ķä¼ļ

-0.27

tein

-0.25

æīĭå·¥

-0.25

ushman

-0.25

åħ¼èģĮ

-0.25

uncture

-0.24

ucha

-0.23

 dash

-0.23

Anc

-0.23

POSITIVE LOGITS

linger

0.27

uspend

0.27

mere

0.26

$results

0.26

opia

0.26

åŃĶéĽĢ

0.26

æ¾Ħæ¸ħ

0.26

pz

0.26

ling

0.25

plr

0.25

Activations Density 0.004%

computer authentication/security

No Comments

No Known Activations