INDEX

Explanations

Global

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

åĿĩåı¯

-0.25

isions

-0.24

æĵį

-0.24

åĲ¦å®ļ

-0.23

ä¹ĥèĩ³

-0.23

ordinates

-0.23

cu

-0.23

 Spartan

-0.23

 Maur

-0.23

çļĦå¤§

-0.23

POSITIVE LOGITS

 clusters

0.25

 ours

0.25

è¯ķ

0.25

âĬķ

0.24

pig

0.24

worth

0.24

binary

0.24

icos

0.24

-cluster

0.24

Øµ

0.24

Activations Density 0.044%

Global

No Comments

No Known Activations