INDEX

Explanations

computer-related/technical documentation

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

æĮ½

-0.26

CAM

-0.26

CHAN

-0.26

inv

-0.25

REW

-0.25

za

-0.25

æ¸¥

-0.25

èħ¾

-0.24

(inv

-0.24

Ath

-0.24

POSITIVE LOGITS

/*@

0.27

 bedtime

0.25

 deduct

0.24

çĽ¸åħ³åĨħå®¹

0.24

 Prison

0.24

ç¼£

0.23

 satur

0.23

çŃ

0.23

ngr

0.23

æĹłæķ°

0.23

Activations Density 0.026%

computer-related/technical documentation

No Comments

No Known Activations