INDEX

Explanations

Code and text snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

est

-0.27

emble

-0.25

amb

-0.24

 Bench

-0.24

wares

-0.24

idelity

-0.23

IBE

-0.23

 proper

-0.23

ilent

-0.23

æĥħæĢĢ

-0.23

POSITIVE LOGITS

RSS

0.27

å·²ç»ıè¢«

0.27

æĥ³æī¾

0.26

çħŀ

0.25

íĥĿ

0.25

ç¢´

0.25

æīŃ

0.25

riz

0.25

æĹ©åľ¨

0.24

åĨĴçĿĢ

0.24

Activations Density 0.000%

Code and text snippets

No Comments

No Known Activations