INDEX

Explanations

athom

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

LETE

-0.29

ORMAT

-0.26

iese

-0.26

setAttribute

-0.25

è¾Ķ

-0.25

 mourning

-0.25

æııç»ĺ

-0.25

åľĮ

-0.25

CodeAt

-0.24

 bolt

-0.24

POSITIVE LOGITS

 coordination

0.28

åħĶ

0.26

_basis

0.24

ä¸ºåķ¥

0.24

 flames

0.24

asis

0.24

monds

0.23

æĪĳä¸įæĺ¯

0.23

 singleton

0.23

 extern

0.23

Activations Density 0.008%

athom

No Comments

No Known Activations