INDEX

Explanations

code/website context

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

tgt

-0.26

lesc

-0.25

gm

-0.25

tgt

-0.25

onal

-0.25

 Valencia

-0.25

 elevated

-0.24

íķ´

-0.24

 Resolver

-0.24

æĬķ

-0.24

POSITIVE LOGITS

ç©°

0.27

éĥ½éľĢè¦ģ

0.26

rottle

0.25

 reprint

0.25

idak

0.25

éĵ¡

0.25

çİĩè¾¾

0.25

distributed

0.25

lok

0.25

enza

0.24

Activations Density 0.023%

code/website context

No Comments

No Known Activations