INDEX

Explanations

programming/technical forum questions

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

éĻįä½İæĪĲæľ¬

-0.28

poi

-0.27

DOM

-0.25

èĨı

-0.25

isi

-0.25

dl

-0.25

argins

-0.24

ÑģÑĤÐ¾Ð»ÑĮ

-0.24

 Poetry

-0.24

DL

-0.24

POSITIVE LOGITS

æŀ¥

0.27

 toes

0.26

çºµ

0.26

æĮģæľīçļĦ

0.25

è¾«

0.25

ODB

0.24

åĽłä¸ºå¥¹

0.24

wick

0.24

 Held

0.24

çł

0.24

Activations Density 0.032%

programming/technical forum questions

No Comments

No Known Activations