INDEX

Explanations

unrelated text snippets

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

åģ¥

-0.26

cling

-0.26

 placements

-0.26

Placement

-0.26

 placement

-0.26

âĦī

-0.25

pray

-0.25

amin

-0.25

izin

-0.24

 Placement

-0.24

POSITIVE LOGITS

 immediate

0.29

é»ĺé»ĺåľ°

0.26

Immediate

0.26

 deferred

0.25

åıĮè¾¹

0.25

 improper

0.24

enko

0.24

 Shortcut

0.24

å¹³çŃī

0.24

ometers

0.24

Activations Density 0.003%

unrelated text snippets

No Comments

No Known Activations