INDEX

Explanations

code or articles titles

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

æŀ¶

-0.27

antt

-0.27

undle

-0.26

uble

-0.25

 exercised

-0.24

 exercising

-0.24

 strokes

-0.24

Esc

-0.24

¹Ħ

-0.24

oop

-0.24

POSITIVE LOGITS

LS

0.29

heits

0.26

cel

0.25

å®ļåĲĳ

0.25

SHOT

0.24

thesis

0.24

LS

0.24

ëį°

0.23

Tex

0.23

ls

0.23

Activations Density 0.025%

code or articles titles

No Comments

No Known Activations