INDEX

Explanations

German

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PMC

-0.29

leigh

-0.28

æĮĸ

-0.28

hit

-0.27

 Consultants

-0.27

dyn

-0.26

ickers

-0.26

orthand

-0.26

çĽĽå¤§

-0.25

ahir

-0.25

POSITIVE LOGITS

å¤¹

0.26

ÙĪØ°

0.25

éĢĥèĦ±

0.25

 Naples

0.25

structuring

0.24

ERRQ

0.24

GEST

0.24

ETH

0.24

TED

0.24

.eth

0.24

Activations Density 0.935%

German

No Comments

No Known Activations