INDEX

Explanations

code and technical text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

~/.

-0.29

éĿ¢åŃĶ

-0.28

\"{

-0.26

åĮĸçŁ³

-0.25

[:,:,

-0.25

:return

-0.24

:image

-0.24

èº«å¤Ħ

-0.24

phans

-0.23

azÄ±

-0.23

POSITIVE LOGITS

nty

0.30

iry

0.28

yr

0.27

çŁ¥éģĵäºĨ

0.26

çŀŃ

0.25

æĬĦ

0.25

.sb

0.24

start

0.24

 Schul

0.24

ifty

0.24

Activations Density 0.112%

code and technical text

No Comments

No Known Activations